检索结果-内蒙古大学图书馆

作者： Wu, Bian Ren, Xiaolin Liu, Chongqing Zhang, Yaxin Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai 200030 China Motorola Labs. China Research Center 38F CITIC Sq. 1168 Nanjing Rd. W. Shanghai 200041 China

When an Automatic Speech recognition (ASR) system is applied in noisy environments, Voice Activity Detection (VAD) is crucial to the performance of the overall system. The employment of the VAD for ASR on embedded mobile systems will minimize physical distractions and make the system convenient to use. Conventional VAD algorithm is of high complexity, which makes it unsuitable for embedded mobile devices;or of low robustness, which holds back its application in mobile noisy environments. In this paper, we propose a robust VAD algorithm specifically designed for ASR on embedded mobile devices. The architecture of the proposed algorithm is based on a two-level decision making strategy, where there is an interaction between a lower features-based level and subsequent decision logic based on a finite-state machine. Many discriminating features are employed in the lower level to improve the robustness of the VAD. The two-level decision strategy allows different features to be used in different states and reduces the cost of the algorithm, which makes the proposed algorithm suitable for embedded mobile devices. The evaluation experiments show the proposed VAD algorithm is robust and contribute to the overall performance gain of the ASR system in various acoustic environments. © 2005 Springer Science+Business Media, Inc.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Human Activity recognition with User-Free Accelerometers in the Sensor Networks

Human Activity Recognition with User-Free Accelerometers in ...

引用

2005 International Conference on Neural Networks and Brain(ICNN&B’05)

作者： Shuangquan Wang Jie Yang Ningjiang Chen Xin Chen Qinfeng Zhang Institute of Image Processing & Pattern Recognition Shanghai Jiaotong University Philips Research East Asia

Many applications using wireless sensor networks (WSNs) aim at providing friendly and intelligent services based on the recognition of human's *** the research result on wearable computing has been fruitful,our experience indicates that a user-free sensor deployment is more natural and acceptable to *** our system,activities were recognized through matching the movement patterns of the objects,which tri-axial accelerometers had been attached to. Several representative features,including accelerations and their fusion,were calculated and three classifiers were tested on these *** with Decision Tree(DT) C4.5 and Multiple-Layer Perception(MLP),Support Vector Machine (SVM) performs relatively well across different tests. Additionally,feature selection will be discussed for better system performance for WSNs.

关键词： Human Activity recognition with User-Free Accelerometers in the Sensor Networks Sensor Activity

来源：评论

学校读者我要写书评

暂无评论

Efficient VLSI architecture for multi-dimensional discrete wavelet transform

Efficient VLSI architecture for multi-dimensional discrete w...

引用

MIPPR 2005: SAR and Multispectral image processing

作者： Xiong, Cheng-Yi Tian, Jin-Wen Liu, Jian College of Electronic Information Engineering South-Center University for Nationalities Wuhan 430074 China Institute of Pattern Recognition and Artificial Intelligence Key Laboratory of Education Ministry for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan 430074 China

Efficient VLSI architectures for multi-dimensional (m-D) discrete wavelet transform (DWT), e.g. m=2, 3, are presented, in which the lifting scheme of DWT is used to reduce efficiently hardware complexity. The parallelism of 2 m subbands transforms in lifting-based m-D DWT is explored, which increases efficiently the throughput rate of separable m-D DWT. The proposed architecture is composed of m2m-1 1-D DWT modules working in parallel and pipelined, which is designed to process 2m input samples per clock cycle, and generate 2m subbands coefficients synchronously. The total time of computing one level of decomposition for a 2-D image (3-D image sequence) of size N2 (MN2) is approximately N2/4 (MN2/8) intra- clock cycles (ccs). An efficient line-based architecture framework for both 2D+t and t+2D 3-D DWT is first proposed. Compared with the similar works reported in previous literature, the proposed architecture has good performance in terms of production of computation time and hardware cost. The proposed architecture is simple, regular, scalable and well suited for VLSI implementation.

关键词： VLSI circuits

来源：评论

学校读者我要写书评

暂无评论

Performing clustering analysis on collaborative models

Performing clustering analysis on collaborative models

引用

作者： Shen, Hongbin Yang, Jie Chen, Ningjiang Dong, Yifei Wang, Shitong Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai 200030 China Philips Research East Asia Shanghai 200070 China School of Computer Science and Engineering University of New South Wales Australia Department of Information Science Southern Yangtze University Wuxi Jiangsu 214036 China

Conventional clustering algorithms are designed for a single independent dataset, i.e. Fuzzy C-Means (FCM) clustering algorithm. In the real world, a dataset is independent of other datasets but sometimes can be cooperative with others by exchanging information, such as the relationship between subsidiary companies. We should therefore consider the influence from other relative collaborative datasets while performing clustering learning under such collaborative circumstances. In this paper, three different collaborative models are discussed and new correct methods are proposed to quantitatively measure such collaboration between datasets, i.e. information gain. The corresponding collaborative clustering algorithms are presented accordingly and the theoretical analysis shows that the new cooperative clustering algorithms can finally converge to a local minimum. Experimental results demonstrate that the clustering structures obtained by new cooperative algorithms are different from those of conventional algorithms for the consideration of collaboration and the performances of these collaborative clustering algorithms can be much better than those conventional single clustering algorithms under the cooperating circumstances. ©?2005-IOS Press and the authors. All rights reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Adaptive nonlinear auto-associative modeling through manifold learning

引用

9th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining, PAKDD 2005

作者： Zhang, Junping Li, Stan Z. Intelligent Information Processing Laboratory Department of Computer Science and Engineering Fudan University Shanghai 200433 China Key Laboratory of Complex Systems and Intelligence Science Chinese Academy of Sciences China National Laboratory of Pattern Recognition Center for Biometrics and Security Research Institute of Automation Beijing 100080 China

ISBN: (纸本)3540260765

We propose adaptive nonlinear auto-associative modeling (ANAM) based on Locally Linear Embedding algorithm (LLE) for learning intrinsic principal features of each concept separately and recognition thereby. Unlike traditional supervised manifold learning algorithm, the proposed ANAM algorithm has several advantages: 1) it implicitly embodies discriminant information because the suboptimal parameters of ANAM are determined based on error rate of the validation set. 2) it avoids the curse of dimensionality without loss accuracy because recognition is completed in the original space. Experiments on character and digit databases show that the advantages of the proposed ANAM algorithm. © Springer-Verlag Berlin Heidelberg 2005.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Outlier detection by weighted mercer-kernel based fuzzy clustering algorithm

引用

Iranian Journal of Electrical and Computer Engineering 2005年第2期4卷 129-136页

作者： Shen, Hongbin Yang, Jie Dong, Yifei Wang, Shitong College of Computer and Information Engineering Hohai University Changzhou Jiangsu China Department of Image Processing and Pattern Recognition Jiaotong University Shanghai China School of Computer Science and Engineering University of New South Wales Australia School of Information Southern Yantze University Wuxi Jiangsu China Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University China IEEE Institute of National Automation Department of Information Southern Yangtse University Polytechnic University of Hongkong Advanced Computing Research Center Bristol University United Kingdom

Outliers are data values that lie away from the general cluster of other data values. Detecting the outliers of a dataset is an important research topic for data cleaning and finding new useful knowledge in many research areas, i.e. data mining, pattern recognition, etc. In the past decades, many useful algorithms were proposed in the literature. In this paper, a new fuzzy kernel-clustering algorithm with outliers (FKCO) is presented to locate critical areas that are often represented by only a few outliers. Theoretic analysis also shows that FKCO can converge to a local minimum of the objective function. Finally, based on the information theory, a new criterion for finding outliers is also proposed. Simulations of different types of datasets demonstrate the feasibility of this new method. © 2005 JD.

关键词： Fuzzy control

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional motion analysis of mitral valve leaflet in children with congenital heart disease and its clinical significance: a pilot study

Three-dimensional motion analysis of mitral valve leaflet in...

引用

Computers in Cardiology (CinC)

作者： K. Sun X. Yan L.P. Yao Q. Guo L.P. Wu Y.F. Shang Shanghai Children's Medical Center XinHua Hospital Affiliated to Medical School of Shanghai Jiao Tong University Shanghai China Institute of Image Processing & Pattern Recognition Shanghai Jiaotong University Shanghai China

This study is to quantitatively evaluate abnormal movement of mitral apparatus (MA) in patient with congenital mitral valve regurgitation using self-designed three dimensional motion analyses software and enable doctors to intuitionistic and "en-face" visualize the mitral valve's movement by using pseudocolor coding of the moving velocity of mitral valve leaflet. Initial evaluation of the software was conducted in 20 children with congenital mitral valve regurgitation (MR) including 10 children with mild MR and 10 children with moderate to severe MR. Results showed that, the moving velocity of the rough zone of mitral valve during systolic phase in children with moderate to severe MR is much high than that in control group. It's indicated that three dimensional motion analysis of mitral valve could emerge to be a new potential useful parameter for evaluation the truly mechanism of MR

关键词： Motion analysis Heart valves Cardiac disease Pediatrics Velocity control Echocardiography Biomedical imaging image coding Hospitals image processing

来源：评论

学校读者我要写书评

暂无评论

An improved mapping method of buffer for line-based architecture of 2-D DWT

An improved mapping method of buffer for line-based architec...

引用

International Conference on Communications, Circuits and Systems (ICCCAS)

作者： Cheng-Yi Xiong Cheng-Jun Wang Jin-wen Tian Jian Liu Institute of Pattern Recognition & Artificial Intelligence Key Laboratory of Education Ministry for Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan China College of Electronic Information Engineering South-Center University for Nationalities Wuhan China

ISBN: (纸本)0780390156

The number of arithmetic units used in the one-dimensional (1D) discrete wavelet transform (DWT) is the main consideration for reducing the area of VLSI implementation of 1D DWT, while the size of intermediate memory used for data buffering is another dominate factor of effecting hardware complexity of VLSI implementation for two-dimensional (2D) DWT. In this paper, we exploit the essential relationship between the size of temporal buffer (TB) required in the line-based architecture for 2D DWT (LBA2DDWT) and the number of registers used in the 1D DWT module, and present an improved method of mapping the registers used in the 1D DWT to the TB required in LBA2DDWT. Comparison results with the other design reported in previous literature demonstrate that, the proposed mapping method can reduce efficiently the size of memory required in LBA2DDWT.

关键词： Discrete wavelet transforms Registers Two dimensional displays Very large scale integration Hardware Convolution Pipeline processing Arithmetic Signal analysis image processing

来源：评论

学校读者我要写书评

暂无评论

ICDAR2005 page segmentation competition

ICDAR2005 page segmentation competition

引用

International Conference on Document Analysis and recognition

作者： A. Antonacopoulos B. Gatos D. Bridson Pattern Recognition and Image Analysis (PRImA) Research Laboratory School of Computing Science and Engineering University of Sanford Manchester UK Computational Intelligence Laboratory National Center for Scientific Research Demokritos Institute of Informatics and Telecommunications Athens Greece

There is an established need for objective evaluation of layout analysis methods, in realistic circumstances. This paper describes the page segmentation competition (modus operandi, dataset and evaluation criteria) held in the context of ICDAR2005 and presents the results of the evaluation of four candidate methods. The main objective of the competition was to compare the performance of such methods using scanned documents from commonly-occurring publications. The results indicate that although methods seem to be maturing, there is still a considerable need to develop robust methods that deal with everyday documents.

关键词： image analysis Performance analysis image segmentation Text analysis Optical character recognition software pattern recognition Telecommunication computing Computational intelligence Laboratories Informatics

来源：评论

学校读者我要写书评

暂无评论

Using string kernel to predict signal peptide cleavage site based on subsite coupling model (vol 28, pg 395, 2005)

引用

AMINO ACIDS 2005年第3期29卷 301-301页

作者： Wang, M Yang, J Chou, KC Institute of Image Processing and Pattern Recognition Shanghai Jiaotong University Shanghai China Microsoft Research Asia Beijing China Institute of Bioinformatics and Drug Discovery Tianjin China Gordon Life Science Institute San Diego U.S.A.

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：